
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
import seaborn as sns


results = pd.read_csv("results.csv", engine="python")
print(results.dtypes)
display(results)

date          object
home_team     object
away_team     object
home_score     int64
away_score     int64
tournament    object
city          object
country       object
neutral         bool
dtype: object


conditions=[ results['home_score']>results['away_score'],results['home_score']==results['away_score'],results['home_score']<results['away_score']]
match_result=[ "home_win", 'draw', 'away_win']

results["result"] = np.select(conditions, match_result)
results


def home_away_draws(df): #returns number of home wins, away wins, draws and total games played 
    home_wins=len(df[df.away_score<df.home_score])
    away_wins=len(df[df.away_score>df.home_score])
    draws=len(df[df.away_score==df.home_score])
    total_games_played=home_wins+away_wins+draws
    avg_home=df['home_score'].mean()
    avg_away=df['away_score'].mean()
    return home_wins,away_wins,draws,total_games_played,avg_home,avg_away


def draw_pie(title, pie): #draw pie chart for draws team
    labels = ['Home wins', 'Away wins', 'Draws']
    sizes = pie
    colors = ['#39375b','#745c97','#d597ce']
    plt.figure(figsize=(15,10))
    fig1, ax1 = plt.subplots()
    plt.title(title)
    patches, texts, autotexts = ax1.pie(sizes, colors = colors, labels=labels, autopct='%1.1f%%', startangle=90)
    for text in texts:
        text.set_color('grey')
    for autotext in autotexts:
        autotext.set_color('white')
    ax1.axis('equal')  
    plt.tight_layout()
    plt.show()


major_tournaments = ['FIFA World Cup','Confederations Cup','Oceania Nations Cup','CCCF Championship','AFC Asian Cup','Copa América','Gold Cup','UEFA Euro','NAFU Championship','African Cup of Nations']

major=results.loc[results['tournament'].isin(major_tournaments) , :]


#All games including matches that were played in nuetral grounds
m_home_wins, m_away_wins, m_draws, m_total_games_played, m_home_score_avg, m_away_score_avg = home_away_draws(major)
print(f'Away wins: {m_away_wins}')
print(f'Home wins: {m_home_wins}')
print(f'Draws: {m_draws}')
print(f'Home side goal per game: {m_home_score_avg}')
print(f'Away side goal per game: {m_away_score_avg}')

m_home_win_percent=m_home_wins/m_total_games_played
m_away_win_percent=m_away_wins/m_total_games_played
m_draw_percent=m_draws/m_total_games_played

print(m_home_win_percent)
print(m_away_win_percent)
print(m_draw_percent)

draw_pie("Home wins vs Away Wins in Neutral Games", [m_home_win_percent,m_away_win_percent,m_draw_percent])

Away wins: 1141
Home wins: 1832
Draws: 863
Home side goal per game: 1.6715328467153285
Away side goal per game: 1.2082898852971846
0.47758081334723673
0.29744525547445255
0.22497393117831074

<Figure size 1080x720 with 0 Axes>


#Matches that were played in either home or away grounds (non-neutral games)
major_nn = major[major['neutral']==False]
nn_m_home_wins, nn_m_away_wins, nn_m_draws, nn_m_total_games_played, nn_m_home_score_avg, nn_m_away_score_avg = home_away_draws(major_nn)

print(f'Away wins: {nn_m_away_wins}')
print(f'Home wins: {nn_m_home_wins}')
print(f'Draws: {nn_m_draws}')
print(f'Home side goal per game: {nn_m_home_score_avg}')
print(f'Away side goal per game: {nn_m_away_score_avg}')

nn_m_home_win_percent=nn_m_home_wins/nn_m_total_games_played
nn_m_away_win_percent=nn_m_away_wins/nn_m_total_games_played
nn_m_draw_percent=nn_m_draws/nn_m_total_games_played

print(nn_m_home_win_percent)
print(nn_m_away_win_percent)
print(nn_m_draw_percent)

draw_pie("Home wins vs Away Wins in Non-Neutral Games",[nn_m_home_win_percent,nn_m_away_win_percent,nn_m_draw_percent])

Away wins: 182
Home wins: 568
Draws: 198
Home side goal per game: 1.9841772151898733
Away side goal per game: 0.9483122362869199
0.5991561181434599
0.19198312236286919
0.2088607594936709

<Figure size 1080x720 with 0 Axes>


#Goals by tournaments 
avg_goal=major.pivot_table(['home_score','away_score'],columns='tournament',aggfunc=np.sum)
avg_goal.loc['total']=avg_goal.sum(axis=0)
avg_goal=avg_goal.T
avg_goal


#Average Goals per Tournament 
count=major['tournament'].value_counts()
count=count.sort_index()
avg_goal['count']=count
avg_goal['avg']=avg_goal['total']/avg_goal['count']
avg_goal


#Above table visualized
plt.figure(figsize=(20,5))
plt.title("Average Goal per Game Based on Tournament")
sns.set_style("darkgrid")
sns.barplot(x=avg_goal.index,y=avg_goal['avg'],color='#d597ce');


#Host country 
matches_hosted=pd.DataFrame()
matches_hosted['counts']=major['country'].value_counts()
matches_hosted['country']=major['country'].value_counts().index
matches_hosted=matches_hosted.reset_index()
matches_hosted.drop(columns=['index'],inplace=True)
matches_hosted


#Conversion of counrtry names to ISO-3661-alpha-3 format for plotly
import pycountry

input_countries = matches_hosted['country']
change={"Netherlands Antilles":"Aruba","United Arab Republic":"Egypt","South Korea":"Korea, Republic of","Bolivia":"Bolivia, Plurinational State of","England":"United Kingdom","Iran":"Iran, Islamic Republic of","Venezuela":"Venezuela, Bolivarian Republic of","Yugoslavia":"Serbia","Ivory Coast":"Côte d'Ivoire","China PR":"Taiwan, Province of China","Vietnam":"Viet Nam","Russia":"Russian Federation"}

for i,country in enumerate(input_countries):
    if country in change:
        input_countries[i]=change[country]

countries = {}
for country in pycountry.countries:
    countries[country.name] = country.alpha_3

codes = [countries.get(country, 'Unknown code') for country in input_countries]
matches_hosted['codes']=codes
matches_hosted

/var/folders/tm/2wrhck9x0kq65jq3116k2c9r0000gn/T/ipykernel_44672/2615724815.py:9: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  input_countries[i]=change[country]


#Cholorpleth of countries based on number of matches hosted
import plotly.graph_objects as go

plt.figure(figsize=(20,20))
fig = go.Figure(data=go.Choropleth(
    locations = matches_hosted['codes'],
    z = matches_hosted['counts'],
    text = "red",
    colorscale = 'reds',
    autocolorscale=False,
    reversescale=False,
    marker_line_color='darkgray',
    marker_line_width=0.5,
    colorbar_title = 'Games hosted',
))

fig.update_layout(
    title_text='Games hosted by Country',
    geo=dict(
        showframe=False,
        showcoastlines=False,
        projection_type='equirectangular'
    ),
    annotations = [dict(
        x=0.55,
        y=0.1,
        xref='paper',
        yref='paper',
        showarrow = False
    )]
)

fig.show()

<Figure size 1440x1440 with 0 Axes>


#Tournament that has had the most games
plt.figure(figsize=(20,5))
plt.title("Tournament games count")
sns.set_style("darkgrid")
sns.barplot(x=avg_goal.index,y=avg_goal['count'],color='#d597ce');


#Goals scored by each team
home_scored=major.pivot_table(['home_score'],columns=["home_team"],aggfunc=np.sum)
home_scored=home_scored.T
away_scored=major.pivot_table(['away_score'],columns=["away_team"],aggfunc=np.sum)
away_scored=away_scored.T
home_scored=home_scored.rename(columns={"home_score":"scored"})
away_scored=away_scored.rename(columns={"away_score":"scored"})
scored_df=home_scored.append(away_scored)
scored_df=scored_df.groupby(level=0).sum()
scored_df


#Goals conceded by each team
home_conceded=major.pivot_table(['away_score'],columns=["home_team"],aggfunc=np.sum)
home_conceded=home_conceded.T
away_conceded=major.pivot_table(['home_score'],columns=["away_team"],aggfunc=np.sum)
away_conceded=away_conceded.T
home_conceded=home_conceded.rename(columns={"away_score":"conceded"})
away_conceded=away_conceded.rename(columns={"home_score":"conceded"})
conceded_df=home_conceded.append(away_conceded)
conceded_df=conceded_df.groupby(level=0).sum()
conceded_df


# Number of games each team has played
home_games=major['home_team'].value_counts()
away_games=major['away_team'].value_counts()
games_count=home_games.append(away_games)
games_count=games_count.groupby(level=0).sum()


#Making a new table out of the data
countries_goals=pd.DataFrame(index=scored_df.index)
countries_goals['scored']=scored_df['scored']
countries_goals['conceded']=conceded_df['conceded']
countries_goals['games_played']=games_count
countries_goals['scored_avg']=countries_goals['scored']/countries_goals['games_played']
countries_goals['conceded_avg']=countries_goals['conceded']/countries_goals['games_played']
countries_goals


#Finding who won,drew or lost from every match 
home_wins_draws_loses=major[['home_team','result']]
home_wins_draws_loses.rename(columns={'home_team':'team'},inplace=True)
home_wins_draws_loses['result']=["win" if x=="home_win" else "draw" if x=="draw" else "lose" for x in home_wins_draws_loses['result']]
away_wins_draws_loses=major[['away_team','result']]
away_wins_draws_loses.rename(columns={'away_team':'team'},inplace=True)
away_wins_draws_loses['result']=["win" if x=="away_win" else "draw" if x=="draw" else "lose" for x in away_wins_draws_loses['result']]
wins_draws_loses_df=home_wins_draws_loses[['team','result']]
wins_draws_loses_df=wins_draws_loses_df.append(away_wins_draws_loses)
wins_draws_loses_df

/Users/arwasaad/opt/anaconda3/lib/python3.8/site-packages/pandas/core/frame.py:5034: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

/Users/arwasaad/opt/anaconda3/lib/python3.8/site-packages/pandas/core/frame.py:3607: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


#Aggregating the counts from the above table 
wins=wins_draws_loses_df.loc[(wins_draws_loses_df['result']=='win')]
wins=wins.groupby('team').count()
draws=wins_draws_loses_df.loc[(wins_draws_loses_df['result']=='draw')]
draws=draws.groupby('team').count()
loses=wins_draws_loses_df.loc[(wins_draws_loses_df['result']=='lose')]
loses=loses.groupby('team').count()

#Another option /major.pivot_table(index=['team','result'],aggfunc='count')['away_score']
#draws
wins
#loses


countries=pd.DataFrame(index=countries_goals.index)
countries['wins']=[wins.loc[x]['result'] if x in wins.index else 0 for x in countries.index]
countries['draws']=[draws.loc[x]['result'] if x in draws.index else 0 for x in countries.index]
countries['loses']=[loses.loc[x]['result'] if x in loses.index else 0 for x in countries.index]
countries['games_played']=countries_goals['games_played']
countries['win_percentage']=((countries['wins']/countries['games_played'])*100).round(2)
countries


countries.loc['Saudi Arabia',:]

wins              27.0000
draws             16.0000
loses             33.0000
games_played      76.0000
win_percentage    35.5300
weight             0.7600
best              54.0056
Name: Saudi Arabia, dtype: float64


#Somewhat of a metric for finding best teams
countries['weight']=countries['games_played']/100
countries['best']=(2*countries['win_percentage'])*countries['weight']


countries.loc[:,['wins','games_played','win_percentage','weight','best']].sort_values('best',ascending=False).head(30)


#Just checking the tail end of the data 
countries.loc[:,['wins','games_played','win_percentage','weight','best']].sort_values('best',ascending=False).tail(60)


#Goals scored
plot_data=countries_goals.sort_values("scored",ascending=False).head(10)
plt.figure(figsize=(15,10))
plt.title("Number of Goals scored")
sns.set_style('darkgrid')
sns.barplot(x=plot_data.index,y=plot_data['scored'],color="#39375b")

<AxesSubplot:title={'center':'Number of Goals scored'}, ylabel='scored'>


#Number of goals conceded 
plot_data=countries_goals.sort_values("conceded",ascending=False).head(10)
plt.figure(figsize=(15,10))
plt.title("Number of Goals conceded")
sns.set_style('darkgrid')
sns.barplot(x=plot_data.index,y=plot_data['conceded'],color="#39375b")

<AxesSubplot:title={'center':'Number of Goals conceded'}, ylabel='conceded'>


plot_data=countries.sort_values("win_percentage",ascending=False).head(10)
plt.figure(figsize=(15,10))
plt.title("Win Percentage")
sns.set_style('darkgrid')
sns.barplot(x=plot_data.index,y=plot_data['win_percentage'],color="#39375b")

<AxesSubplot:title={'center':'Win Percentage'}, ylabel='win_percentage'>


plot_data=countries.sort_values("best",ascending=False).head(10)
plt.figure(figsize=(15,10))
plt.title("Custom Best team metric")
sns.set_style('darkgrid')
sns.barplot(x=plot_data.index,y=plot_data['best'],color="#39375b")

<AxesSubplot:title={'center':'Custom Best team metric'}, ylabel='best'>

	date	home_team	away_team	home_score	away_score	tournament	city	country	neutral
0	1872-11-30	Scotland	England	0	0	Friendly	Glasgow	Scotland	False
1	1873-03-08	England	Scotland	4	2	Friendly	London	England	False
2	1874-03-07	Scotland	England	2	1	Friendly	Glasgow	Scotland	False
3	1875-03-06	England	Scotland	2	2	Friendly	London	England	False
4	1876-03-04	Scotland	England	3	0	Friendly	Glasgow	Scotland	False
...	...	...	...	...	...	...	...	...	...
42423	2021-07-06	Trinidad and Tobago	French Guiana	1	1	Gold Cup qualification	Fort Lauderdale	United States	True
42424	2021-07-07	England	Denmark	2	1	UEFA Euro	London	England	False
42425	2021-07-09	Peru	Colombia	2	3	Copa América	Brasília	Brazil	True
42426	2021-07-10	Brazil	Argentina	0	1	Copa América	Rio de Janeiro	Brazil	False
42427	2021-07-11	England	Italy	1	1	UEFA Euro	London	England	False

	date	home_team	away_team	home_score	away_score	tournament	city	country	neutral	result
0	1872-11-30	Scotland	England	0	0	Friendly	Glasgow	Scotland	False	draw
1	1873-03-08	England	Scotland	4	2	Friendly	London	England	False	home_win
2	1874-03-07	Scotland	England	2	1	Friendly	Glasgow	Scotland	False	home_win
3	1875-03-06	England	Scotland	2	2	Friendly	London	England	False	draw
4	1876-03-04	Scotland	England	3	0	Friendly	Glasgow	Scotland	False	home_win
...	...	...	...	...	...	...	...	...	...	...
42423	2021-07-06	Trinidad and Tobago	French Guiana	1	1	Gold Cup qualification	Fort Lauderdale	United States	True	draw
42424	2021-07-07	England	Denmark	2	1	UEFA Euro	London	England	False	home_win
42425	2021-07-09	Peru	Colombia	2	3	Copa América	Brasília	Brazil	True	away_win
42426	2021-07-10	Brazil	Argentina	0	1	Copa América	Rio de Janeiro	Brazil	False	away_win
42427	2021-07-11	England	Italy	1	1	UEFA Euro	London	England	False	draw

	away_score	home_score	total
tournament
AFC Asian Cup	429	558	987
African Cup of Nations	723	948	1671
CCCF Championship	193	356	549
Confederations Cup	193	230	423
Copa América	1077	1594	2671
FIFA World Cup	1136	1412	2548
Gold Cup	336	567	903
NAFU Championship	11	17	28
Oceania Nations Cup	156	282	438
UEFA Euro	381	448	829

	away_score	home_score	total	count	avg
tournament
AFC Asian Cup	429	558	987	370	2.667568
African Cup of Nations	723	948	1671	690	2.421739
CCCF Championship	193	356	549	123	4.463415
Confederations Cup	193	230	423	140	3.021429
Copa América	1077	1594	2671	841	3.175981
FIFA World Cup	1136	1412	2548	900	2.831111
Gold Cup	336	567	903	327	2.761468
NAFU Championship	11	17	28	7	4.000000
Oceania Nations Cup	156	282	438	101	4.336634
UEFA Euro	381	448	829	337	2.459941

	counts	country
0	393	United States
1	239	Brazil
2	168	France
3	160	Argentina
4	155	Chile
...	...	...
78	4	Hungary
79	3	United Arab Republic
80	3	Canada
81	3	Azerbaijan
82	1	Wales

Major Tournaments¶

Home or Away?¶

Average goal per game¶

Countries that have hosted the most games¶

Country Wise data¶

	scored
Albania	1
Algeria	106
Angola	31
Argentina	633
Aruba	8
...	...
Yemen	0
Yemen DPR	0
Yugoslavia	69
Zambia	81
Zimbabwe	13

	scored	conceded	games_played	scored_avg	conceded_avg
Albania	1	3	3	0.333333	1.000000
Algeria	106	104	87	1.218391	1.195402
Angola	31	41	29	1.068966	1.413793
Argentina	633	289	293	2.160410	0.986348
Aruba	8	9	5	1.600000	1.800000
...	...	...	...	...	...
Yemen	0	10	3	0.000000	3.333333
Yemen DPR	0	9	2	0.000000	4.500000
Yugoslavia	69	68	43	1.604651	1.581395
Zambia	81	69	67	1.208955	1.029851
Zimbabwe	13	27	12	1.083333	2.250000

	team	result
438	Chile	lose
440	Argentina	win
441	Brazil	draw
442	Argentina	draw
444	Brazil	lose
...	...	...
42420	Spain	draw
42424	Denmark	lose
42425	Colombia	win
42426	Argentina	win
42427	Italy	draw

	result
team
Albania	1
Algeria	31
Angola	4
Argentina	175
Aruba	1
...	...
Vietnam	2
Wales	6
Yugoslavia	16
Zambia	26
Zimbabwe	2

	wins	draws	loses	games_played	win_percentage
Albania	1	0	2	3	33.33
Algeria	31	24	32	87	35.63
Angola	4	14	11	29	13.79
Argentina	175	60	58	293	59.73
Aruba	1	1	3	5	20.00
...	...	...	...	...	...
Yemen	0	0	3	3	0.00
Yemen DPR	0	0	2	2	0.00
Yugoslavia	16	8	19	43	37.21
Zambia	26	20	21	67	38.81
Zimbabwe	2	2	8	12	16.67

	wins	games_played	win_percentage	weight	best
Brazil	212	347	61.10	3.47	424.0340
Argentina	175	293	59.73	2.93	350.0178
Uruguay	141	272	51.84	2.72	282.0096
Germany	102	175	58.29	1.75	204.0150
Mexico	102	210	48.57	2.10	203.9940
United States	81	149	54.36	1.49	161.9928
Chile	79	228	34.65	2.28	158.0040
Paraguay	72	206	34.95	2.06	143.9940
Italy	69	136	50.74	1.36	138.0128
France	64	119	53.78	1.19	127.9964
Peru	63	183	34.43	1.83	126.0138
Colombia	63	166	37.95	1.66	125.9940
Costa Rica	62	135	45.93	1.35	124.0110
Nigeria	59	120	49.17	1.20	118.0080
Egypt	58	113	51.33	1.13	116.0058
Spain	58	119	48.74	1.19	116.0012
Ghana	58	111	52.25	1.11	115.9950
Cameroon	49	118	41.53	1.18	98.0108
Netherlands	47	89	52.81	0.89	94.0018
Ivory Coast	45	106	42.45	1.06	89.9940
South Korea	44	111	39.64	1.11	88.0008
England	44	107	41.12	1.07	87.9968
Iran	43	83	51.81	0.83	86.0046
Japan	40	91	43.96	0.91	80.0072
Australia	39	76	51.32	0.76	78.0064
Portugal	36	74	48.65	0.74	72.0020
Russia	33	84	39.29	0.84	66.0072
Honduras	33	87	37.93	0.87	65.9982
Belgium	31	70	44.29	0.70	62.0060
Algeria	31	87	35.63	0.87	61.9962

	wins	games_played	win_percentage	weight	best
Papua New Guinea	3	14	21.43	0.14	6.0004
Slovakia	3	11	27.27	0.11	5.9994
Norway	3	11	27.27	0.11	5.9994
Libya	3	11	27.27	0.11	5.9994
Togo	3	28	10.71	0.28	5.9976
Zimbabwe	2	12	16.67	0.12	4.0008
Burma	2	4	50.00	0.04	4.0000
Madagascar	2	5	40.00	0.05	4.0000
Iceland	2	8	25.00	0.08	4.0000
Vietnam	2	9	22.22	0.09	3.9996
German DR	2	6	33.33	0.06	3.9996
Indonesia	2	13	15.38	0.13	3.9988
Kenya	2	17	11.76	0.17	3.9984
Thailand	2	24	8.33	0.24	3.9984
Nicaragua	2	35	5.71	0.35	3.9970
Taiwan	1	7	14.29	0.07	2.0006
Cape Verde	1	7	14.29	0.07	2.0006
Malawi	1	6	16.67	0.06	2.0004
Lebanon	1	6	16.67	0.06	2.0004
Cambodia	1	5	20.00	0.05	2.0000
Kyrgyzstan	1	4	25.00	0.04	2.0000
Liberia	1	5	20.00	0.05	2.0000
Sierra Leone	1	5	20.00	0.05	2.0000
Singapore	1	4	25.00	0.04	2.0000
Aruba	1	5	20.00	0.05	2.0000
Bosnia and Herzegovina	1	3	33.33	0.03	1.9998
Albania	1	3	33.33	0.03	1.9998
Bermuda	1	3	33.33	0.03	1.9998
Slovenia	1	9	11.11	0.09	1.9998
Malaysia	1	9	11.11	0.09	1.9998
Rwanda	1	3	33.33	0.03	1.9998
Finland	1	3	33.33	0.03	1.9998
Cook Islands	0	4	0.00	0.04	0.0000
Benin	0	14	0.00	0.14	0.0000
Botswana	0	3	0.00	0.03	0.0000
Burundi	0	3	0.00	0.03	0.0000
Vietnam Republic	0	6	0.00	0.06	0.0000
Belize	0	3	0.00	0.03	0.0000
Yemen	0	3	0.00	0.03	0.0000
Yemen DPR	0	2	0.00	0.02	0.0000
Bangladesh	0	4	0.00	0.04	0.0000
Turkmenistan	0	6	0.00	0.06	0.0000
Palestine	0	6	0.00	0.06	0.0000
French Guiana	0	3	0.00	0.03	0.0000
Saint Vincent and the Grenadines	0	2	0.00	0.02	0.0000
Philippines	0	3	0.00	0.03	0.0000
Niger	0	6	0.00	0.06	0.0000
Namibia	0	9	0.00	0.09	0.0000
Mozambique	0	12	0.00	0.12	0.0000
Mauritius	0	3	0.00	0.03	0.0000
Mauritania	0	3	0.00	0.03	0.0000
Samoa	0	6	0.00	0.06	0.0000
Tanzania	0	6	0.00	0.06	0.0000
Latvia	0	3	0.00	0.03	0.0000
Suriname	0	1	0.00	0.01	0.0000
Hong Kong	0	10	0.00	0.10	0.0000
North Macedonia	0	3	0.00	0.03	0.0000
Guinea-Bissau	0	6	0.00	0.06	0.0000
Grenada	0	6	0.00	0.06	0.0000
Guyana	0	3	0.00	0.03	0.0000